Learning Optimal Control Policy for Unknown Discrete-Time Systems.
Jing LaiJunlin XiongPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2023)
Keyphrases
- control policy
- learning systems
- learning process
- reinforcement learning
- approximate dynamic programming
- educational systems
- long run
- complex systems
- online learning
- supervised learning
- expert systems
- graphical models
- knowledge acquisition
- dynamic programming
- search space
- optimal control
- lower bound
- control policies
- search algorithm
- machine learning